mlsanityData to 7 Oct 2026

Let the Agent Steer: Closed-Loop Ranking Optimization via Influence Exchange

arXiv 2603.27765 ↗First posted 29 Mar 2026cs.AIcited by 4

On the map: LLM agents and tool use → Agentic recommender systems

Abstract (arXiv)

Recommendation ranking is fundamentally an influence allocation problem: a sorting formula distributes ranking influence among competing factors, and the business outcome depends on finding the optimal "exchange rates" among them. However, offline proxy metrics systematically misjudge how influence reallocation translates to online impact, with asymmetric bias across metrics that a single calibration factor cannot correct. We present Sortify, the first fully autonomous LLM-driven ranking optimization agent deployed in a large-scale production recommendation system. The agent reframes ranking optimization as continuous influence exchange, closing the full loop from diagnosis to parameter deployment without human intervention. It addresses structural problems through three mechanisms: (1) a dual-channel framework grounded in Savage's Subjective Expected Utility (SEU) that decouples offline-online transfer correction (Belief channel) from constraint penalty adjustment (Preference channel); (2) an LLM meta-controller operating on framework-level parameters rather than low-level search variables; (3) a persistent Memory DB with 7 relational tables for cross-round learning. Its core metric, Influence Share, provides a decomposable measure where all factor contributions sum to exactly 100%. Sortify has been deployed across two markets. In Country A, the agent pushed GMV from -3.6% to +9.2% within 7 rounds with peak orders reaching +12.5%. In Country B, a cold-start deployment achieved +4.15% GMV/UU and +3.58% Ads Revenue in a 7-day A/B test, leading to full production rollout.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Agentic recommender systems, one of 16 directions in LLM agents and tool use. Builds on 6 of its 15 references that are in the map. First posted on arXiv 29 Mar 2026.

Builds on

6 of 15 references.

References · 6

  1. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,455
  2. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  3. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,313
  4. 2015Doubly Robust Policy Evaluation and Optimizationcited by 158
  5. 2018Offline A/B testing for Recommender Systemscited by 94
  6. 2019On Application of Learning to Rank for E-Commerce Searchcited by 24

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026RecHarness: A Bandit-Routed Agentic Harness for Self-Evolving Recommender Systemscited by 3
  2. 2026EvoRec: Self Evolving Agentic Recommender Systemscited by 1
  3. 2026Attacking and Defending Multi-Agent Collaborative Filtering Systems Through Connectivitycited by 0
  4. 2026PEAR: Progressive Evidence-Based AutoResearch for Industrial Search Systemscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026CORAL: An LLM-Native Harness for Production Recommender Systems
  2. 2026Decoding ML Decision: An Agentic Reasoning Framework for Large-Scale Ranking System
  3. 2026Rethinking Recommendation Paradigms: From Pipelines to Agentic Recommender Systems
  4. 2026RankEvolve: A Reliable Multi-Agent Auto-Research Harness for Evolving Ranking Models
  5. 2026FlexRec: Adapting LLM-based Recommenders for Flexible Needs via Reinforcement Learning
  6. 2026Self-Evolving Recommendation System: End-To-End Autonomous Model Optimization With LLM Agents
  7. 2026Reasoning to Rank: An End-to-End Solution for Exploiting Large Language Models for Recommendation
  8. 2026Position: Recommender Systems Should Move Beyond Platform-Centric Ranking toward Personal Agent-Mediated Recommendation